Amirali Baniasadi
Papers
2
Total Citations
12
H-Index
2
About
Amirali Baniasadi is a researcher at the forefront of explainable artificial intelligence (XAI) and deep learning for robotics and condition monitoring. His work focuses on demystifying the "black box" nature of deep neural networks, particularly in safety-critical applications where trust and interpretability are paramount. Baniasadi’s most influential contribution is his unified XAI framework for signal-based deep learning models (2024, 8 citations), which directly addresses the adoption barriers of AI in mission-critical machinery and robotic systems. He has also advanced sound source localization (SSL) through deep learning (2025, 4 citations), enabling robots to pinpoint acoustic events for navigation, human-machine dialogue, and condition monitoring. By bridging the gap between complex neural architectures and practical, trustworthy deployment, Baniasadi’s work has significant implications for industrial automation and autonomous systems. His research not only pushes the boundaries of AI transparency but also ensures that deep learning can be reliably integrated into real-world robotic applications where operational safety is non-negotiable.
Research Focus
Key Achievements
Top Papers
- 1
- 2